Skip to content

scikit-bio Toolkit

Lets an agent analyze biological sequences, alignments, phylogenetic trees and microbiome diversity with scikit-bio.

Stars
55,780
Licence
MIT
Files
3 files

What it does

Once installed, the agent knows how to use the scikit-bio Python library for biology work: reading and writing DNA, RNA and protein sequence files (FASTA, FASTQ, GenBank, Newick), aligning sequences, building and comparing phylogenetic trees, and computing microbiome diversity measures such as alpha/beta diversity, UniFrac, PCoA ordination and PERMANOVA. It supplies tested code patterns and notes on pitfalls, such as specifying FASTQ quality offsets and genetic codes explicitly. The skill is documentation and guidance; the agent still writes and runs the Python code itself.

Great for

  • Bioinformatics students learning sequence analysis and alignment in Python
  • Microbiome or ecology researchers running diversity and PERMANOVA analyses
  • Developers building pipelines that read FASTA or Newick files and build trees

Skip it if

  • Clinical or diagnostic decisions, since the examples use small synthetic fixtures and the skill notes that filename-based templates are not validated workflows
  • Users who need BLAST database searches or E-values, because the wrapper scoring resembles BLAST but is not a BLAST search

Try asking

  • “Align these two DNA sequences with local alignment and show the CIGAR string”
  • “Compute Bray-Curtis beta diversity and run PERMANOVA on my microbiome OTU table”
  • “Build a neighbor-joining tree from this distance matrix and compare it with my reference Newick tree”
  • “Translate this FASTA mRNA sequence to protein, handling incomplete codons”
Step-by-step guide: how to use scikit-bio ToolkitInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    scikit-bio.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip scikit-bio.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip scikit-bio.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the exact file paths and FASTQ quality encoding (for example phred_offset=33) so it does not guess.
  • Verify numerical results against a small known example before using them in publications.
  • Install the pinned scikit-bio version in a virtual environment, since the skill targets 0.7.4 specifically.

What's inside

  • references/api_reference.md
  • references/review.md
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.